neuralop.data.transforms.normalizers.DictUnitGaussianNormalizer
- class neuralop.data.transforms.normalizers.DictUnitGaussianNormalizer(normalizer_dict: Dict[str, UnitGaussianNormalizer], input_mappings: Dict[str, slice], return_mappings: Dict[str, slice])[source]
DictUnitGaussianNormalizer composes DictTransform and UnitGaussianNormalizer to normalize different fields of a model output tensor to Gaussian distributions w/ mean 0 and unit variance.
- Parameters:
- normalizer_dictDict[str, UnitGaussianNormalizer]
dictionary of normalizers, keyed to fields
- input_mappingsDict[slice]
slices of input tensor to grab per field, must share keys with above
- return_mappingsDict[slice]
_description_
Methods
from_dataset(dataset[, dim, keys, mask])Return a dictionary of normalizer instances, fitted on the given dataset
- classmethod from_dataset(dataset, dim=None, keys=None, mask=None)[source]
Return a dictionary of normalizer instances, fitted on the given dataset
- Parameters:
- datasetpytorch dataset
each element must be a dict {key: sample} e.g. {‘x’: input_samples, ‘y’: target_labels}
- dimint list, default is None
If None, reduce over all dims (scalar mean and std)
Otherwise, must include batch-dimensions and all over dims to reduce over
- keysstr list or None
if not None, a normalizer is instanciated only for the given keys